從購買意願資料中挖掘高度相關性的關聯規則

Mining Association Rules with High Correlation from the Purchasing Intension Data

10.6382/JIM.201110.0119

翁政雄(Cheng-Hsiung Weng)

資料探勘 ； 關聯規則 ； 關聯分析 ； data mining ； association rule ； corelation analysis

資訊管理學報

18卷4期（2011 / 10 / 01）

119 - 138

繁體中文

關聯規則探勘技術是一項重要的資料挖掘技術，這項技術可以從交易資料庫中挖掘消費者購買行為之間的關聯性。現今的行銷策略皆視顧客為公司重要的獲利來源。因此，公司應該積極尋找潛在的顧客，並發展合適的行銷策略以吸引他們。為達上述目的，許多公司已經開始積極收集相關資料庫，並嘗試從這些資料庫中找出有意義的規則，藉以發展合適的行銷策略以吸引這些潛在顧客。本研究探討如何利用關聯規則分析消費者購買手機的決策考量因素，利用關聯規則之支持度與信心度分析消費者基本資料與手機產品特性之間的關聯性，以提供給行銷部門及產品設計部門分別作為行銷策略制定之參考與設計出更符合消費者的產品。然而，使用∑-count方式累計過多具有低支持度的項目集時，卻容易產生不具關聯性的高頻項目集。因此，本研究發展新的方法嘗試從消費者的購買意願中挖掘有意義且有關聯性的規則。此方法乃是運用α-cut的概念過濾不具關聯性的低支持度項目，並且利用相關係數（lift）進一步強化現有挖掘關聯規則的基本機制（支持度-信心度），嘗試從消費者購買意願資料中找出有意義且相關的規則。實驗結果顯示本研究所提出的方法可以找出有價值且具有高度相關的關聯規則。

Association rule mining is an important data analysis method that can discover associations within data. This technique can mine the associations between the consumer's behaviors. The current marketing strategies perceive customers as important resources to a company for making more profit. Therefore, it is essential to companies to successfully discover potential customers and then develop new marketing strategies to attract them. To achieve these aims, many companies have gathered significant numbers of large databases to discover meaningful patterns and then develop new marketing strategies to attract the potential customers. However, using the ∑-count, the summation of a large number of itemsets with very small support may induce irrelevant associations. To this end, this study proposes a new approach to discover interesting and relevant patterns from consumer's purchasing intension. This approach is based on the α-cut method to filter out the irrelevant patterns with small support. Furthermore, a correlation measure, also known as lift, is used to augment the support-confidence framework for association rules. Next, we develop an algorithm to discover relevant and interesting association rules from purchasing intensions. Experimental results from the survey data show that the proposed approach can help to discover interesting and valuable patterns with high correlation.

1. International Business Machines, IBM Intelligent Miner User's Guide, Version 1, Release 1, 1996..
2. Agrawal, R.,Imieliski, T.,Swami, A.(1993).Mining association rules between sets of items in large databases.Proceedings of ACM SIGMOD
3. Agrawal, R.,Srikant, R.(1994).Fast algorithms for mining association rules.Proceedings of the 20th International Conference on Very Large Data Bases,Santiago, Chile:
4. Berry, M.,Linoff, G.(1997).Data Mining Techniques: For Marketing, Sales, and Customer Support.NY:Wiley.
5. Bodjanova, S.(2002).A generalized α-cut.Fuzzy Sets and Systems,126(2),157-176.
6. Chen, M.S.,Han, J.,Yu, P.S.(1996).Data Mining: An overview from a database perspective.IEEE Trans Knowledge and Data Engineering,8(6),866-883.
7. Chen, Y.L.,Tang, K.,Shen, R.J.,Hu, Y.H.(2005).Market basket analysis in a multiple store environment.Decision Support Systems,40(2),339-354.
8. Chen, Y.L.,Weng, C.H.(2008).Mining association rules from imprecise ordinal data.Fuzzy sets and systems,159(4),460-474.
9. Djouadi, Y.,Redaoui, S.,Amroun, K.(2007).Mining fuzzy association rules from uncertain data.IEEE International Fuzzy Systems Conference,London:
10. Han, J.,Kamber, W.(2001).Data Mining: Concepts and Techniques.San Francisco, CA:Morgan Kaufmann.
11. Hong, T.P.,Kuo, C.S.,Chi, S.C.(1999).Mining association rules from quantitative data.Intelligent Data Analysis,3(5),363-376.
12. Hu, Y.C.,Chen, R.S.,Tzeng, G.H.(2003).Discovering fuzzy association rules using fuzzy partition methods.Knowledge-Based System,16(3),137-147.
13. Kotler, P.,Keller, K.L.(2001).A framework for marketing management.Upper Saddle River, New Jersey:Pearson Education.
14. Lian, W.,Cheung, D.W.,Yiu, S.M.(2005).An efficient algorithm for finding dense regions for mining quantitative association rules.Computers and Mathematics with Applications,50(3-4),471-490.
15. Lin, C.,Hong, C.(2008).Using customer knowledge in designing electronic catalog.Expert Systems with Applications,34(1),119-127.
16. Shepard, D.(1998).The New Direct Marketing: How to Implement a Profit-Driven Database Marketing Strategy.:David Shepard Associates.
17. Srikant, R.,Vu, Q.,Agrawal, R.(1996).Mining Association Rules with Item Constraints.SIGMOD International Conference on Management of Data
18. Tseng, M.C.,Lin, W.Y.,Jeng, R.(2008).Incremental maintenance of generalized association rules under taxonomy evolution.Journal of Information Science,34(2),174-195.
19. Yang, T.C.,Lai, H.(2006).Comparison of product bundling strategies on different online shopping behaviors.Electronic Commerce Research and Applications,5(4),295-304.
20. Zadeh, L.A.(1971).Quantitative fuzzy semantics.Information Sciences,3(2),159-176.

1. 魏慧美,郭隆興,林子堯(2023)。教師在職進修研習課程大數據關聯規則研究初探：以2017年全國國中語文領域國文科教師為例。測驗學刊，70(3)，221-248。
2. 楊亞澄、翁政雄、胡雅涵(2016)。運用關聯規則及改變探勘技術於防火牆政策規則優化。資訊管理學報，23(3)，277-304。
3. 張益誠,張育傑,余泰毅(2021)。探討環境教育論文的文件自動分類技術－以2013－2018年環境教育研討會摘要為例。環境教育研究，17(1)，85-128。